1/* SPDX-License-Identifier: GPL-2.0-only */
2/*
3 * Kernel-based Virtual Machine driver for Linux
4 *
5 * This header defines architecture specific interfaces, x86 version
6 */
7
8#ifndef _ASM_X86_KVM_HOST_H
9#define _ASM_X86_KVM_HOST_H
10
11#include <linux/types.h>
12#include <linux/mm.h>
13#include <linux/mmu_notifier.h>
14#include <linux/tracepoint.h>
15#include <linux/cpumask.h>
16#include <linux/irq_work.h>
17#include <linux/irq.h>
18
19#include <linux/kvm.h>
20#include <linux/kvm_para.h>
21#include <linux/kvm_types.h>
22#include <linux/perf_event.h>
23#include <linux/pvclock_gtod.h>
24#include <linux/clocksource.h>
25#include <linux/irqbypass.h>
26#include <linux/hyperv.h>
27
28#include <asm/apic.h>
29#include <asm/pvclock-abi.h>
30#include <asm/desc.h>
31#include <asm/mtrr.h>
32#include <asm/msr-index.h>
33#include <asm/asm.h>
34#include <asm/kvm_page_track.h>
35#include <asm/kvm_vcpu_regs.h>
36#include <asm/hyperv-tlfs.h>
37
38#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
39
40#define KVM_MAX_VCPUS 288
41#define KVM_SOFT_MAX_VCPUS 240
42#define KVM_MAX_VCPU_ID 1023
43#define KVM_USER_MEM_SLOTS 509
44/* memory slots that are not exposed to userspace */
45#define KVM_PRIVATE_MEM_SLOTS 3
46#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
47
48#define KVM_HALT_POLL_NS_DEFAULT 200000
49
50#define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
51
52#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
53					KVM_DIRTY_LOG_INITIALLY_SET)
54
55/* x86-specific vcpu->requests bit members */
56#define KVM_REQ_MIGRATE_TIMER		KVM_ARCH_REQ(0)
57#define KVM_REQ_REPORT_TPR_ACCESS	KVM_ARCH_REQ(1)
58#define KVM_REQ_TRIPLE_FAULT		KVM_ARCH_REQ(2)
59#define KVM_REQ_MMU_SYNC		KVM_ARCH_REQ(3)
60#define KVM_REQ_CLOCK_UPDATE		KVM_ARCH_REQ(4)
61#define KVM_REQ_LOAD_MMU_PGD		KVM_ARCH_REQ(5)
62#define KVM_REQ_EVENT			KVM_ARCH_REQ(6)
63#define KVM_REQ_APF_HALT		KVM_ARCH_REQ(7)
64#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(8)
65#define KVM_REQ_NMI			KVM_ARCH_REQ(9)
66#define KVM_REQ_PMU			KVM_ARCH_REQ(10)
67#define KVM_REQ_PMI			KVM_ARCH_REQ(11)
68#define KVM_REQ_SMI			KVM_ARCH_REQ(12)
69#define KVM_REQ_MASTERCLOCK_UPDATE	KVM_ARCH_REQ(13)
70#define KVM_REQ_MCLOCK_INPROGRESS \
71	KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
72#define KVM_REQ_SCAN_IOAPIC \
73	KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
74#define KVM_REQ_GLOBAL_CLOCK_UPDATE	KVM_ARCH_REQ(16)
75#define KVM_REQ_APIC_PAGE_RELOAD \
76	KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
77#define KVM_REQ_HV_CRASH		KVM_ARCH_REQ(18)
78#define KVM_REQ_IOAPIC_EOI_EXIT		KVM_ARCH_REQ(19)
79#define KVM_REQ_HV_RESET		KVM_ARCH_REQ(20)
80#define KVM_REQ_HV_EXIT			KVM_ARCH_REQ(21)
81#define KVM_REQ_HV_STIMER		KVM_ARCH_REQ(22)
82#define KVM_REQ_LOAD_EOI_EXITMAP	KVM_ARCH_REQ(23)
83#define KVM_REQ_GET_NESTED_STATE_PAGES	KVM_ARCH_REQ(24)
84#define KVM_REQ_APICV_UPDATE \
85	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
86#define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
87#define KVM_REQ_TLB_FLUSH_GUEST \
88	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
89#define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
90#define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
91
92#define CR0_RESERVED_BITS                                               \
93	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
94			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
95			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
96
97#define CR4_RESERVED_BITS                                               \
98	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
99			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
100			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
101			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
102			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
103			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
104
105#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
106
107
108
109#define INVALID_PAGE (~(hpa_t)0)
110#define VALID_PAGE(x) ((x) != INVALID_PAGE)
111
112#define UNMAPPED_GVA (~(gpa_t)0)
113
114/* KVM Hugepage definitions for x86 */
115#define KVM_MAX_HUGEPAGE_LEVEL	PG_LEVEL_1G
116#define KVM_NR_PAGE_SIZES	(KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1)
117#define KVM_HPAGE_GFN_SHIFT(x)	(((x) - 1) * 9)
118#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
119#define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
120#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
121#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
122
123static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
124{
125	/* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */
126	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
127		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
128}
129
130#define KVM_PERMILLE_MMU_PAGES 20
131#define KVM_MIN_ALLOC_MMU_PAGES 64UL
132#define KVM_MMU_HASH_SHIFT 12
133#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
134#define KVM_MIN_FREE_MMU_PAGES 5
135#define KVM_REFILL_PAGES 25
136#define KVM_MAX_CPUID_ENTRIES 256
137#define KVM_NR_FIXED_MTRR_REGION 88
138#define KVM_NR_VAR_MTRR 8
139
140#define ASYNC_PF_PER_VCPU 64
141
142enum kvm_reg {
143	VCPU_REGS_RAX = __VCPU_REGS_RAX,
144	VCPU_REGS_RCX = __VCPU_REGS_RCX,
145	VCPU_REGS_RDX = __VCPU_REGS_RDX,
146	VCPU_REGS_RBX = __VCPU_REGS_RBX,
147	VCPU_REGS_RSP = __VCPU_REGS_RSP,
148	VCPU_REGS_RBP = __VCPU_REGS_RBP,
149	VCPU_REGS_RSI = __VCPU_REGS_RSI,
150	VCPU_REGS_RDI = __VCPU_REGS_RDI,
151#ifdef CONFIG_X86_64
152	VCPU_REGS_R8  = __VCPU_REGS_R8,
153	VCPU_REGS_R9  = __VCPU_REGS_R9,
154	VCPU_REGS_R10 = __VCPU_REGS_R10,
155	VCPU_REGS_R11 = __VCPU_REGS_R11,
156	VCPU_REGS_R12 = __VCPU_REGS_R12,
157	VCPU_REGS_R13 = __VCPU_REGS_R13,
158	VCPU_REGS_R14 = __VCPU_REGS_R14,
159	VCPU_REGS_R15 = __VCPU_REGS_R15,
160#endif
161	VCPU_REGS_RIP,
162	NR_VCPU_REGS,
163
164	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
165	VCPU_EXREG_CR0,
166	VCPU_EXREG_CR3,
167	VCPU_EXREG_CR4,
168	VCPU_EXREG_RFLAGS,
169	VCPU_EXREG_SEGMENTS,
170	VCPU_EXREG_EXIT_INFO_1,
171	VCPU_EXREG_EXIT_INFO_2,
172};
173
174enum {
175	VCPU_SREG_ES,
176	VCPU_SREG_CS,
177	VCPU_SREG_SS,
178	VCPU_SREG_DS,
179	VCPU_SREG_FS,
180	VCPU_SREG_GS,
181	VCPU_SREG_TR,
182	VCPU_SREG_LDTR,
183};
184
185enum exit_fastpath_completion {
186	EXIT_FASTPATH_NONE,
187	EXIT_FASTPATH_REENTER_GUEST,
188	EXIT_FASTPATH_EXIT_HANDLED,
189};
190typedef enum exit_fastpath_completion fastpath_t;
191
192struct x86_emulate_ctxt;
193struct x86_exception;
194enum x86_intercept;
195enum x86_intercept_stage;
196
197#define KVM_NR_DB_REGS	4
198
199#define DR6_BD		(1 << 13)
200#define DR6_BS		(1 << 14)
201#define DR6_BT		(1 << 15)
202#define DR6_RTM		(1 << 16)
203#define DR6_FIXED_1	0xfffe0ff0
204#define DR6_INIT	0xffff0ff0
205#define DR6_VOLATILE	0x0001e00f
206
207#define DR7_BP_EN_MASK	0x000000ff
208#define DR7_GE		(1 << 9)
209#define DR7_GD		(1 << 13)
210#define DR7_FIXED_1	0x00000400
211#define DR7_VOLATILE	0xffff2bff
212
213#define PFERR_PRESENT_BIT 0
214#define PFERR_WRITE_BIT 1
215#define PFERR_USER_BIT 2
216#define PFERR_RSVD_BIT 3
217#define PFERR_FETCH_BIT 4
218#define PFERR_PK_BIT 5
219#define PFERR_GUEST_FINAL_BIT 32
220#define PFERR_GUEST_PAGE_BIT 33
221
222#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
223#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
224#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
225#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
226#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
227#define PFERR_PK_MASK (1U << PFERR_PK_BIT)
228#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
229#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
230
231#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK |	\
232				 PFERR_WRITE_MASK |		\
233				 PFERR_PRESENT_MASK)
234
235/* apic attention bits */
236#define KVM_APIC_CHECK_VAPIC	0
237/*
238 * The following bit is set with PV-EOI, unset on EOI.
239 * We detect PV-EOI changes by guest by comparing
240 * this bit with PV-EOI in guest memory.
241 * See the implementation in apic_update_pv_eoi.
242 */
243#define KVM_APIC_PV_EOI_PENDING	1
244
245struct kvm_kernel_irq_routing_entry;
246
247/*
248 * the pages used as guest page table on soft mmu are tracked by
249 * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
250 * by indirect shadow page can not be more than 15 bits.
251 *
252 * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access,
253 * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
254 */
255union kvm_mmu_page_role {
256	u32 word;
257	struct {
258		unsigned level:4;
259		unsigned gpte_is_8_bytes:1;
260		unsigned quadrant:2;
261		unsigned direct:1;
262		unsigned access:3;
263		unsigned invalid:1;
264		unsigned nxe:1;
265		unsigned cr0_wp:1;
266		unsigned smep_andnot_wp:1;
267		unsigned smap_andnot_wp:1;
268		unsigned ad_disabled:1;
269		unsigned guest_mode:1;
270		unsigned :6;
271
272		/*
273		 * This is left at the top of the word so that
274		 * kvm_memslots_for_spte_role can extract it with a
275		 * simple shift.  While there is room, give it a whole
276		 * byte so it is also faster to load it from memory.
277		 */
278		unsigned smm:8;
279	};
280};
281
282union kvm_mmu_extended_role {
283/*
284 * This structure complements kvm_mmu_page_role caching everything needed for
285 * MMU configuration. If nothing in both these structures changed, MMU
286 * re-configuration can be skipped. @valid bit is set on first usage so we don't
287 * treat all-zero structure as valid data.
288 */
289	u32 word;
290	struct {
291		unsigned int valid:1;
292		unsigned int execonly:1;
293		unsigned int cr0_pg:1;
294		unsigned int cr4_pae:1;
295		unsigned int cr4_pse:1;
296		unsigned int cr4_pke:1;
297		unsigned int cr4_smap:1;
298		unsigned int cr4_smep:1;
299		unsigned int cr4_la57:1;
300		unsigned int maxphyaddr:6;
301	};
302};
303
304union kvm_mmu_role {
305	u64 as_u64;
306	struct {
307		union kvm_mmu_page_role base;
308		union kvm_mmu_extended_role ext;
309	};
310};
311
312struct kvm_rmap_head {
313	unsigned long val;
314};
315
316struct kvm_pio_request {
317	unsigned long linear_rip;
318	unsigned long count;
319	int in;
320	int port;
321	int size;
322};
323
324#define PT64_ROOT_MAX_LEVEL 5
325
326struct rsvd_bits_validate {
327	u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL];
328	u64 bad_mt_xwr;
329};
330
331struct kvm_mmu_root_info {
332	gpa_t pgd;
333	hpa_t hpa;
334};
335
336#define KVM_MMU_ROOT_INFO_INVALID \
337	((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE })
338
339#define KVM_MMU_NUM_PREV_ROOTS 3
340
341struct kvm_mmu_page;
342
343/*
344 * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
345 * and 2-level 32-bit).  The kvm_mmu structure abstracts the details of the
346 * current mmu mode.
347 */
348struct kvm_mmu {
349	unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu);
350	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
351	int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
352			  bool prefault);
353	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
354				  struct x86_exception *fault);
355	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
356			    u32 access, struct x86_exception *exception);
357	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
358			       struct x86_exception *exception);
359	int (*sync_page)(struct kvm_vcpu *vcpu,
360			 struct kvm_mmu_page *sp);
361	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa);
362	hpa_t root_hpa;
363	gpa_t root_pgd;
364	union kvm_mmu_role mmu_role;
365	u8 root_level;
366	u8 shadow_root_level;
367	u8 ept_ad;
368	bool direct_map;
369	struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS];
370
371	/*
372	 * Bitmap; bit set = permission fault
373	 * Byte index: page fault error code [4:1]
374	 * Bit index: pte permissions in ACC_* format
375	 */
376	u8 permissions[16];
377
378	/*
379	* The pkru_mask indicates if protection key checks are needed.  It
380	* consists of 16 domains indexed by page fault error code bits [4:1],
381	* with PFEC.RSVD replaced by ACC_USER_MASK from the page tables.
382	* Each domain has 2 bits which are ANDed with AD and WD from PKRU.
383	*/
384	u32 pkru_mask;
385
386	u64 *pae_root;
387	u64 *lm_root;
388
389	/*
390	 * check zero bits on shadow page table entries, these
391	 * bits include not only hardware reserved bits but also
392	 * the bits spte never used.
393	 */
394	struct rsvd_bits_validate shadow_zero_check;
395
396	struct rsvd_bits_validate guest_rsvd_check;
397
398	/* Can have large pages at levels 2..last_nonleaf_level-1. */
399	u8 last_nonleaf_level;
400
401	bool nx;
402
403	u64 pdptrs[4]; /* pae */
404};
405
406struct kvm_tlb_range {
407	u64 start_gfn;
408	u64 pages;
409};
410
411enum pmc_type {
412	KVM_PMC_GP = 0,
413	KVM_PMC_FIXED,
414};
415
416struct kvm_pmc {
417	enum pmc_type type;
418	u8 idx;
419	u64 counter;
420	u64 eventsel;
421	struct perf_event *perf_event;
422	struct kvm_vcpu *vcpu;
423	/*
424	 * eventsel value for general purpose counters,
425	 * ctrl value for fixed counters.
426	 */
427	u64 current_config;
428};
429
430struct kvm_pmu {
431	unsigned nr_arch_gp_counters;
432	unsigned nr_arch_fixed_counters;
433	unsigned available_event_types;
434	u64 fixed_ctr_ctrl;
435	u64 fixed_ctr_ctrl_mask;
436	u64 global_ctrl;
437	u64 global_status;
438	u64 global_ovf_ctrl;
439	u64 counter_bitmask[2];
440	u64 global_ctrl_mask;
441	u64 global_ovf_ctrl_mask;
442	u64 reserved_bits;
443	u64 raw_event_mask;
444	u8 version;
445	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
446	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
447	struct irq_work irq_work;
448	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
449	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
450	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
451
452	/*
453	 * The gate to release perf_events not marked in
454	 * pmc_in_use only once in a vcpu time slice.
455	 */
456	bool need_cleanup;
457
458	/*
459	 * The total number of programmed perf_events and it helps to avoid
460	 * redundant check before cleanup if guest don't use vPMU at all.
461	 */
462	u8 event_count;
463};
464
465struct kvm_pmu_ops;
466
467enum {
468	KVM_DEBUGREG_BP_ENABLED = 1,
469	KVM_DEBUGREG_WONT_EXIT = 2,
470	KVM_DEBUGREG_RELOAD = 4,
471};
472
473struct kvm_mtrr_range {
474	u64 base;
475	u64 mask;
476	struct list_head node;
477};
478
479struct kvm_mtrr {
480	struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
481	mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
482	u64 deftype;
483
484	struct list_head head;
485};
486
487/* Hyper-V SynIC timer */
488struct kvm_vcpu_hv_stimer {
489	struct hrtimer timer;
490	int index;
491	union hv_stimer_config config;
492	u64 count;
493	u64 exp_time;
494	struct hv_message msg;
495	bool msg_pending;
496};
497
498/* Hyper-V synthetic interrupt controller (SynIC)*/
499struct kvm_vcpu_hv_synic {
500	u64 version;
501	u64 control;
502	u64 msg_page;
503	u64 evt_page;
504	atomic64_t sint[HV_SYNIC_SINT_COUNT];
505	atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT];
506	DECLARE_BITMAP(auto_eoi_bitmap, 256);
507	DECLARE_BITMAP(vec_bitmap, 256);
508	bool active;
509	bool dont_zero_synic_pages;
510};
511
512/* Hyper-V per vcpu emulation context */
513struct kvm_vcpu_hv {
514	u32 vp_index;
515	u64 hv_vapic;
516	s64 runtime_offset;
517	struct kvm_vcpu_hv_synic synic;
518	struct kvm_hyperv_exit exit;
519	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
520	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
521	cpumask_t tlb_flush;
522};
523
524struct kvm_vcpu_arch {
525	/*
526	 * rip and regs accesses must go through
527	 * kvm_{register,rip}_{read,write} functions.
528	 */
529	unsigned long regs[NR_VCPU_REGS];
530	u32 regs_avail;
531	u32 regs_dirty;
532
533	unsigned long cr0;
534	unsigned long cr0_guest_owned_bits;
535	unsigned long cr2;
536	unsigned long cr3;
537	unsigned long cr4;
538	unsigned long cr4_guest_owned_bits;
539	unsigned long cr4_guest_rsvd_bits;
540	unsigned long cr8;
541	u32 host_pkru;
542	u32 pkru;
543	u32 hflags;
544	u64 efer;
545	u64 apic_base;
546	struct kvm_lapic *apic;    /* kernel irqchip context */
547	bool apicv_active;
548	bool load_eoi_exitmap_pending;
549	DECLARE_BITMAP(ioapic_handled_vectors, 256);
550	unsigned long apic_attention;
551	int32_t apic_arb_prio;
552	int mp_state;
553	u64 ia32_misc_enable_msr;
554	u64 smbase;
555	u64 smi_count;
556	bool at_instruction_boundary;
557	bool tpr_access_reporting;
558	bool xsaves_enabled;
559	u64 ia32_xss;
560	u64 microcode_version;
561	u64 arch_capabilities;
562	u64 perf_capabilities;
563
564	/*
565	 * Paging state of the vcpu
566	 *
567	 * If the vcpu runs in guest mode with two level paging this still saves
568	 * the paging mode of the l1 guest. This context is always used to
569	 * handle faults.
570	 */
571	struct kvm_mmu *mmu;
572
573	/* Non-nested MMU for L1 */
574	struct kvm_mmu root_mmu;
575
576	/* L1 MMU when running nested */
577	struct kvm_mmu guest_mmu;
578
579	/*
580	 * Paging state of an L2 guest (used for nested npt)
581	 *
582	 * This context will save all necessary information to walk page tables
583	 * of an L2 guest. This context is only initialized for page table
584	 * walking and not for faulting since we never handle l2 page faults on
585	 * the host.
586	 */
587	struct kvm_mmu nested_mmu;
588
589	/*
590	 * Pointer to the mmu context currently used for
591	 * gva_to_gpa translations.
592	 */
593	struct kvm_mmu *walk_mmu;
594
595	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
596	struct kvm_mmu_memory_cache mmu_shadow_page_cache;
597	struct kvm_mmu_memory_cache mmu_gfn_array_cache;
598	struct kvm_mmu_memory_cache mmu_page_header_cache;
599
600	/*
601	 * QEMU userspace and the guest each have their own FPU state.
602	 * In vcpu_run, we switch between the user and guest FPU contexts.
603	 * While running a VCPU, the VCPU thread will have the guest FPU
604	 * context.
605	 *
606	 * Note that while the PKRU state lives inside the fpu registers,
607	 * it is switched out separately at VMENTER and VMEXIT time. The
608	 * "guest_fpu" state here contains the guest FPU context, with the
609	 * host PRKU bits.
610	 */
611	struct fpu *user_fpu;
612	struct fpu *guest_fpu;
613
614	u64 xcr0;
615	u64 guest_supported_xcr0;
616
617	struct kvm_pio_request pio;
618	void *pio_data;
619
620	u8 event_exit_inst_len;
621
622	struct kvm_queued_exception {
623		bool pending;
624		bool injected;
625		bool has_error_code;
626		u8 nr;
627		u32 error_code;
628		unsigned long payload;
629		bool has_payload;
630		u8 nested_apf;
631	} exception;
632
633	struct kvm_queued_interrupt {
634		bool injected;
635		bool soft;
636		u8 nr;
637	} interrupt;
638
639	int halt_request; /* real mode on Intel only */
640
641	int cpuid_nent;
642	struct kvm_cpuid_entry2 *cpuid_entries;
643
644	unsigned long cr3_lm_rsvd_bits;
645	int maxphyaddr;
646	int max_tdp_level;
647
648	/* emulate context */
649
650	struct x86_emulate_ctxt *emulate_ctxt;
651	bool emulate_regs_need_sync_to_vcpu;
652	bool emulate_regs_need_sync_from_vcpu;
653	int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
654
655	gpa_t time;
656	struct pvclock_vcpu_time_info hv_clock;
657	unsigned int hw_tsc_khz;
658	struct gfn_to_hva_cache pv_time;
659	bool pv_time_enabled;
660	/* set guest stopped flag in pvclock flags field */
661	bool pvclock_set_guest_stopped_request;
662
663	struct {
664		u8 preempted;
665		u64 msr_val;
666		u64 last_steal;
667		struct gfn_to_hva_cache cache;
668	} st;
669
670	u64 l1_tsc_offset;
671	u64 tsc_offset;
672	u64 last_guest_tsc;
673	u64 last_host_tsc;
674	u64 tsc_offset_adjustment;
675	u64 this_tsc_nsec;
676	u64 this_tsc_write;
677	u64 this_tsc_generation;
678	bool tsc_catchup;
679	bool tsc_always_catchup;
680	s8 virtual_tsc_shift;
681	u32 virtual_tsc_mult;
682	u32 virtual_tsc_khz;
683	s64 ia32_tsc_adjust_msr;
684	u64 msr_ia32_power_ctl;
685	u64 tsc_scaling_ratio;
686
687	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
688	unsigned nmi_pending; /* NMI queued after currently running handler */
689	bool nmi_injected;    /* Trying to inject an NMI this entry */
690	bool smi_pending;    /* SMI queued after currently running handler */
691
692	struct kvm_mtrr mtrr_state;
693	u64 pat;
694
695	unsigned switch_db_regs;
696	unsigned long db[KVM_NR_DB_REGS];
697	unsigned long dr6;
698	unsigned long dr7;
699	unsigned long eff_db[KVM_NR_DB_REGS];
700	unsigned long guest_debug_dr7;
701	u64 msr_platform_info;
702	u64 msr_misc_features_enables;
703
704	u64 mcg_cap;
705	u64 mcg_status;
706	u64 mcg_ctl;
707	u64 mcg_ext_ctl;
708	u64 *mce_banks;
709
710	/* Cache MMIO info */
711	u64 mmio_gva;
712	unsigned mmio_access;
713	gfn_t mmio_gfn;
714	u64 mmio_gen;
715
716	struct kvm_pmu pmu;
717
718	/* used for guest single stepping over the given code position */
719	unsigned long singlestep_rip;
720
721	struct kvm_vcpu_hv hyperv;
722
723	cpumask_var_t wbinvd_dirty_mask;
724
725	unsigned long last_retry_eip;
726	unsigned long last_retry_addr;
727
728	struct {
729		bool halted;
730		gfn_t gfns[ASYNC_PF_PER_VCPU];
731		struct gfn_to_hva_cache data;
732		u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */
733		u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
734		u16 vec;
735		u32 id;
736		bool send_user_only;
737		u32 host_apf_flags;
738		unsigned long nested_apf_token;
739		bool delivery_as_pf_vmexit;
740		bool pageready_pending;
741	} apf;
742
743	/* OSVW MSRs (AMD only) */
744	struct {
745		u64 length;
746		u64 status;
747	} osvw;
748
749	struct {
750		u64 msr_val;
751		struct gfn_to_hva_cache data;
752	} pv_eoi;
753
754	u64 msr_kvm_poll_control;
755
756	/*
757	 * Indicates the guest is trying to write a gfn that contains one or
758	 * more of the PTEs used to translate the write itself, i.e. the access
759	 * is changing its own translation in the guest page tables.  KVM exits
760	 * to userspace if emulation of the faulting instruction fails and this
761	 * flag is set, as KVM cannot make forward progress.
762	 *
763	 * If emulation fails for a write to guest page tables, KVM unprotects
764	 * (zaps) the shadow page for the target gfn and resumes the guest to
765	 * retry the non-emulatable instruction (on hardware).  Unprotecting the
766	 * gfn doesn't allow forward progress for a self-changing access because
767	 * doing so also zaps the translation for the gfn, i.e. retrying the
768	 * instruction will hit a !PRESENT fault, which results in a new shadow
769	 * page and sends KVM back to square one.
770	 */
771	bool write_fault_to_shadow_pgtable;
772
773	/* set at EPT violation at this point */
774	unsigned long exit_qualification;
775
776	/* pv related host specific info */
777	struct {
778		bool pv_unhalted;
779	} pv;
780
781	int pending_ioapic_eoi;
782	int pending_external_vector;
783
784	/* be preempted when it's in kernel-mode(cpl=0) */
785	bool preempted_in_kernel;
786
787	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
788	bool l1tf_flush_l1d;
789
790	/* Host CPU on which VM-entry was most recently attempted */
791	unsigned int last_vmentry_cpu;
792
793	/* AMD MSRC001_0015 Hardware Configuration */
794	u64 msr_hwcr;
795
796	/* pv related cpuid info */
797	struct {
798		/*
799		 * value of the eax register in the KVM_CPUID_FEATURES CPUID
800		 * leaf.
801		 */
802		u32 features;
803
804		/*
805		 * indicates whether pv emulation should be disabled if features
806		 * are not present in the guest's cpuid
807		 */
808		bool enforce;
809	} pv_cpuid;
810};
811
812struct kvm_lpage_info {
813	int disallow_lpage;
814};
815
816struct kvm_arch_memory_slot {
817	struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES];
818	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
819	unsigned short *gfn_track[KVM_PAGE_TRACK_MAX];
820};
821
822/*
823 * We use as the mode the number of bits allocated in the LDR for the
824 * logical processor ID.  It happens that these are all powers of two.
825 * This makes it is very easy to detect cases where the APICs are
826 * configured for multiple modes; in that case, we cannot use the map and
827 * hence cannot use kvm_irq_delivery_to_apic_fast either.
828 */
829#define KVM_APIC_MODE_XAPIC_CLUSTER          4
830#define KVM_APIC_MODE_XAPIC_FLAT             8
831#define KVM_APIC_MODE_X2APIC                16
832
833struct kvm_apic_map {
834	struct rcu_head rcu;
835	u8 mode;
836	u32 max_apic_id;
837	union {
838		struct kvm_lapic *xapic_flat_map[8];
839		struct kvm_lapic *xapic_cluster_map[16][4];
840	};
841	struct kvm_lapic *phys_map[];
842};
843
844/* Hyper-V synthetic debugger (SynDbg)*/
845struct kvm_hv_syndbg {
846	struct {
847		u64 control;
848		u64 status;
849		u64 send_page;
850		u64 recv_page;
851		u64 pending_page;
852	} control;
853	u64 options;
854};
855
856/* Hyper-V emulation context */
857struct kvm_hv {
858	struct mutex hv_lock;
859	u64 hv_guest_os_id;
860	u64 hv_hypercall;
861	u64 hv_tsc_page;
862
863	/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
864	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
865	u64 hv_crash_ctl;
866
867	struct ms_hyperv_tsc_page tsc_ref;
868
869	struct idr conn_to_evt;
870
871	u64 hv_reenlightenment_control;
872	u64 hv_tsc_emulation_control;
873	u64 hv_tsc_emulation_status;
874
875	/* How many vCPUs have VP index != vCPU index */
876	atomic_t num_mismatched_vp_indexes;
877
878	struct hv_partition_assist_pg *hv_pa_pg;
879	struct kvm_hv_syndbg hv_syndbg;
880};
881
882struct msr_bitmap_range {
883	u32 flags;
884	u32 nmsrs;
885	u32 base;
886	unsigned long *bitmap;
887};
888
889enum kvm_irqchip_mode {
890	KVM_IRQCHIP_NONE,
891	KVM_IRQCHIP_KERNEL,       /* created with KVM_CREATE_IRQCHIP */
892	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
893};
894
895struct kvm_x86_msr_filter {
896	u8 count;
897	bool default_allow:1;
898	struct msr_bitmap_range ranges[16];
899};
900
901#define APICV_INHIBIT_REASON_DISABLE    0
902#define APICV_INHIBIT_REASON_HYPERV     1
903#define APICV_INHIBIT_REASON_NESTED     2
904#define APICV_INHIBIT_REASON_IRQWIN     3
905#define APICV_INHIBIT_REASON_PIT_REINJ  4
906#define APICV_INHIBIT_REASON_X2APIC	5
907
908struct kvm_arch {
909	unsigned long n_used_mmu_pages;
910	unsigned long n_requested_mmu_pages;
911	unsigned long n_max_mmu_pages;
912	unsigned int indirect_shadow_pages;
913	u8 mmu_valid_gen;
914	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
915	/*
916	 * Hash table of struct kvm_mmu_page.
917	 */
918	struct list_head active_mmu_pages;
919	struct list_head zapped_obsolete_pages;
920	struct list_head lpage_disallowed_mmu_pages;
921	struct kvm_page_track_notifier_node mmu_sp_tracker;
922	struct kvm_page_track_notifier_head track_notifier_head;
923
924	struct list_head assigned_dev_head;
925	struct iommu_domain *iommu_domain;
926	bool iommu_noncoherent;
927#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
928	atomic_t noncoherent_dma_count;
929#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
930	atomic_t assigned_device_count;
931	struct kvm_pic *vpic;
932	struct kvm_ioapic *vioapic;
933	struct kvm_pit *vpit;
934	atomic_t vapics_in_nmi_mode;
935	struct mutex apic_map_lock;
936	struct kvm_apic_map *apic_map;
937	atomic_t apic_map_dirty;
938
939	bool apic_access_page_done;
940	unsigned long apicv_inhibit_reasons;
941
942	gpa_t wall_clock;
943
944	bool mwait_in_guest;
945	bool hlt_in_guest;
946	bool pause_in_guest;
947	bool cstate_in_guest;
948
949	unsigned long irq_sources_bitmap;
950	s64 kvmclock_offset;
951	raw_spinlock_t tsc_write_lock;
952	u64 last_tsc_nsec;
953	u64 last_tsc_write;
954	u32 last_tsc_khz;
955	u64 cur_tsc_nsec;
956	u64 cur_tsc_write;
957	u64 cur_tsc_offset;
958	u64 cur_tsc_generation;
959	int nr_vcpus_matched_tsc;
960
961	spinlock_t pvclock_gtod_sync_lock;
962	bool use_master_clock;
963	u64 master_kernel_ns;
964	u64 master_cycle_now;
965	struct delayed_work kvmclock_update_work;
966	struct delayed_work kvmclock_sync_work;
967
968	struct kvm_xen_hvm_config xen_hvm_config;
969
970	/* reads protected by irq_srcu, writes by irq_lock */
971	struct hlist_head mask_notifier_list;
972
973	struct kvm_hv hyperv;
974
975	#ifdef CONFIG_KVM_MMU_AUDIT
976	int audit_point;
977	#endif
978
979	bool backwards_tsc_observed;
980	bool boot_vcpu_runs_old_kvmclock;
981	u32 bsp_vcpu_id;
982
983	u64 disabled_quirks;
984
985	enum kvm_irqchip_mode irqchip_mode;
986	u8 nr_reserved_ioapic_pins;
987
988	bool disabled_lapic_found;
989
990	bool x2apic_format;
991	bool x2apic_broadcast_quirk_disabled;
992
993	bool guest_can_read_msr_platform_info;
994	bool exception_payload_enabled;
995
996	bool bus_lock_detection_enabled;
997
998	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
999	u32 user_space_msr_mask;
1000
1001	struct kvm_x86_msr_filter __rcu *msr_filter;
1002
1003	struct kvm_pmu_event_filter *pmu_event_filter;
1004	struct task_struct *nx_lpage_recovery_thread;
1005
1006	/*
1007	 * Whether the TDP MMU is enabled for this VM. This contains a
1008	 * snapshot of the TDP MMU module parameter from when the VM was
1009	 * created and remains unchanged for the life of the VM. If this is
1010	 * true, TDP MMU handler functions will run for various MMU
1011	 * operations.
1012	 */
1013	bool tdp_mmu_enabled;
1014
1015	/* List of struct tdp_mmu_pages being used as roots */
1016	struct list_head tdp_mmu_roots;
1017	/* List of struct tdp_mmu_pages not being used as roots */
1018	struct list_head tdp_mmu_pages;
1019};
1020
1021struct kvm_vm_stat {
1022	ulong mmu_shadow_zapped;
1023	ulong mmu_pte_write;
1024	ulong mmu_pde_zapped;
1025	ulong mmu_flooded;
1026	ulong mmu_recycled;
1027	ulong mmu_cache_miss;
1028	ulong mmu_unsync;
1029	ulong remote_tlb_flush;
1030	ulong lpages;
1031	ulong nx_lpage_splits;
1032	ulong max_mmu_page_hash_collisions;
1033};
1034
1035struct kvm_vcpu_stat {
1036	u64 pf_fixed;
1037	u64 pf_guest;
1038	u64 tlb_flush;
1039	u64 invlpg;
1040
1041	u64 exits;
1042	u64 io_exits;
1043	u64 mmio_exits;
1044	u64 signal_exits;
1045	u64 irq_window_exits;
1046	u64 nmi_window_exits;
1047	u64 l1d_flush;
1048	u64 halt_exits;
1049	u64 halt_successful_poll;
1050	u64 halt_attempted_poll;
1051	u64 halt_poll_invalid;
1052	u64 halt_wakeup;
1053	u64 request_irq_exits;
1054	u64 irq_exits;
1055	u64 host_state_reload;
1056	u64 fpu_reload;
1057	u64 insn_emulation;
1058	u64 insn_emulation_fail;
1059	u64 hypercalls;
1060	u64 irq_injections;
1061	u64 nmi_injections;
1062	u64 req_event;
1063	u64 halt_poll_success_ns;
1064	u64 halt_poll_fail_ns;
1065	u64 preemption_reported;
1066	u64 preemption_other;
1067};
1068
1069struct x86_instruction_info;
1070
1071struct msr_data {
1072	bool host_initiated;
1073	u32 index;
1074	u64 data;
1075};
1076
1077struct kvm_lapic_irq {
1078	u32 vector;
1079	u16 delivery_mode;
1080	u16 dest_mode;
1081	bool level;
1082	u16 trig_mode;
1083	u32 shorthand;
1084	u32 dest_id;
1085	bool msi_redir_hint;
1086};
1087
1088static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
1089{
1090	return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
1091}
1092
1093struct kvm_x86_ops {
1094	int (*hardware_enable)(void);
1095	void (*hardware_disable)(void);
1096	void (*hardware_unsetup)(void);
1097	bool (*cpu_has_accelerated_tpr)(void);
1098	bool (*has_emulated_msr)(u32 index);
1099	void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu);
1100
1101	unsigned int vm_size;
1102	int (*vm_init)(struct kvm *kvm);
1103	void (*vm_destroy)(struct kvm *kvm);
1104
1105	/* Create, but do not attach this VCPU */
1106	int (*vcpu_create)(struct kvm_vcpu *vcpu);
1107	void (*vcpu_free)(struct kvm_vcpu *vcpu);
1108	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
1109
1110	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
1111	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
1112	void (*vcpu_put)(struct kvm_vcpu *vcpu);
1113
1114	void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
1115	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
1116	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
1117	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
1118	void (*get_segment)(struct kvm_vcpu *vcpu,
1119			    struct kvm_segment *var, int seg);
1120	int (*get_cpl)(struct kvm_vcpu *vcpu);
1121	void (*set_segment)(struct kvm_vcpu *vcpu,
1122			    struct kvm_segment *var, int seg);
1123	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
1124	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
1125	bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr0);
1126	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
1127	int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
1128	void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
1129	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
1130	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
1131	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
1132	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
1133	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
1134	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
1135	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
1136	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
1137
1138	void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
1139	void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
1140	int  (*tlb_remote_flush)(struct kvm *kvm);
1141	int  (*tlb_remote_flush_with_range)(struct kvm *kvm,
1142			struct kvm_tlb_range *range);
1143
1144	/*
1145	 * Flush any TLB entries associated with the given GVA.
1146	 * Does not need to flush GPA->HPA mappings.
1147	 * Can potentially get non-canonical addresses through INVLPGs, which
1148	 * the implementation may choose to ignore if appropriate.
1149	 */
1150	void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
1151
1152	/*
1153	 * Flush any TLB entries created by the guest.  Like tlb_flush_gva(),
1154	 * does not need to flush GPA->HPA mappings.
1155	 */
1156	void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
1157
1158	enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
1159	int (*handle_exit)(struct kvm_vcpu *vcpu,
1160		enum exit_fastpath_completion exit_fastpath);
1161	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
1162	void (*update_emulated_instruction)(struct kvm_vcpu *vcpu);
1163	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
1164	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
1165	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
1166				unsigned char *hypercall_addr);
1167	void (*set_irq)(struct kvm_vcpu *vcpu);
1168	void (*set_nmi)(struct kvm_vcpu *vcpu);
1169	void (*queue_exception)(struct kvm_vcpu *vcpu);
1170	void (*cancel_injection)(struct kvm_vcpu *vcpu);
1171	int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
1172	int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
1173	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
1174	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
1175	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
1176	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
1177	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
1178	bool (*check_apicv_inhibit_reasons)(ulong bit);
1179	void (*pre_update_apicv_exec_ctrl)(struct kvm *kvm, bool activate);
1180	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
1181	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
1182	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
1183	bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
1184	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
1185	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
1186	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
1187	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
1188	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
1189	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
1190	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
1191	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
1192
1193	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long pgd,
1194			     int pgd_level);
1195
1196	bool (*has_wbinvd_exit)(void);
1197
1198	/* Returns actual tsc_offset set in active VMCS */
1199	u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
1200
1201	/*
1202	 * Retrieve somewhat arbitrary exit information.  Intended to be used
1203	 * only from within tracepoints to avoid VMREADs when tracing is off.
1204	 */
1205	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
1206			      u32 *exit_int_info, u32 *exit_int_info_err_code);
1207
1208	int (*check_intercept)(struct kvm_vcpu *vcpu,
1209			       struct x86_instruction_info *info,
1210			       enum x86_intercept_stage stage,
1211			       struct x86_exception *exception);
1212	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
1213
1214	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
1215
1216	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
1217
1218	/*
1219	 * Arch-specific dirty logging hooks. These hooks are only supposed to
1220	 * be valid if the specific arch has hardware-accelerated dirty logging
1221	 * mechanism. Currently only for PML on VMX.
1222	 *
1223	 *  - slot_enable_log_dirty:
1224	 *	called when enabling log dirty mode for the slot.
1225	 *  - slot_disable_log_dirty:
1226	 *	called when disabling log dirty mode for the slot.
1227	 *	also called when slot is created with log dirty disabled.
1228	 *  - flush_log_dirty:
1229	 *	called before reporting dirty_bitmap to userspace.
1230	 *  - enable_log_dirty_pt_masked:
1231	 *	called when reenabling log dirty for the GFNs in the mask after
1232	 *	corresponding bits are cleared in slot->dirty_bitmap.
1233	 */
1234	void (*slot_enable_log_dirty)(struct kvm *kvm,
1235				      struct kvm_memory_slot *slot);
1236	void (*slot_disable_log_dirty)(struct kvm *kvm,
1237				       struct kvm_memory_slot *slot);
1238	void (*flush_log_dirty)(struct kvm *kvm);
1239	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
1240					   struct kvm_memory_slot *slot,
1241					   gfn_t offset, unsigned long mask);
1242
1243	/* pmu operations of sub-arch */
1244	const struct kvm_pmu_ops *pmu_ops;
1245	const struct kvm_x86_nested_ops *nested_ops;
1246
1247	/*
1248	 * Architecture specific hooks for vCPU blocking due to
1249	 * HLT instruction.
1250	 * Returns for .pre_block():
1251	 *    - 0 means continue to block the vCPU.
1252	 *    - 1 means we cannot block the vCPU since some event
1253	 *        happens during this period, such as, 'ON' bit in
1254	 *        posted-interrupts descriptor is set.
1255	 */
1256	int (*pre_block)(struct kvm_vcpu *vcpu);
1257	void (*post_block)(struct kvm_vcpu *vcpu);
1258
1259	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
1260	void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
1261
1262	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
1263			      uint32_t guest_irq, bool set);
1264	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
1265	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
1266
1267	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
1268			    bool *expired);
1269	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
1270
1271	void (*setup_mce)(struct kvm_vcpu *vcpu);
1272
1273	int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
1274	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
1275	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
1276	void (*enable_smi_window)(struct kvm_vcpu *vcpu);
1277
1278	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
1279	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
1280	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
1281	void (*guest_memory_reclaimed)(struct kvm *kvm);
1282
1283	int (*get_msr_feature)(struct kvm_msr_entry *entry);
1284
1285	bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, void *insn, int insn_len);
1286
1287	bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
1288	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
1289
1290	void (*migrate_timers)(struct kvm_vcpu *vcpu);
1291	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
1292};
1293
1294struct kvm_x86_nested_ops {
1295	void (*leave_nested)(struct kvm_vcpu *vcpu);
1296	int (*check_events)(struct kvm_vcpu *vcpu);
1297	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
1298	int (*get_state)(struct kvm_vcpu *vcpu,
1299			 struct kvm_nested_state __user *user_kvm_nested_state,
1300			 unsigned user_data_size);
1301	int (*set_state)(struct kvm_vcpu *vcpu,
1302			 struct kvm_nested_state __user *user_kvm_nested_state,
1303			 struct kvm_nested_state *kvm_state);
1304	bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu);
1305	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
1306
1307	int (*enable_evmcs)(struct kvm_vcpu *vcpu,
1308			    uint16_t *vmcs_version);
1309	uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu);
1310};
1311
1312struct kvm_x86_init_ops {
1313	int (*cpu_has_kvm_support)(void);
1314	int (*disabled_by_bios)(void);
1315	int (*check_processor_compatibility)(void);
1316	int (*hardware_setup)(void);
1317	bool (*intel_pt_intr_in_guest)(void);
1318
1319	struct kvm_x86_ops *runtime_ops;
1320};
1321
1322struct kvm_arch_async_pf {
1323	u32 token;
1324	gfn_t gfn;
1325	unsigned long cr3;
1326	bool direct_map;
1327};
1328
1329extern u64 __read_mostly host_efer;
1330extern bool __read_mostly allow_smaller_maxphyaddr;
1331extern struct kvm_x86_ops kvm_x86_ops;
1332
1333#define __KVM_HAVE_ARCH_VM_ALLOC
1334static inline struct kvm *kvm_arch_alloc_vm(void)
1335{
1336	return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
1337}
1338void kvm_arch_free_vm(struct kvm *kvm);
1339
1340#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
1341static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
1342{
1343	if (kvm_x86_ops.tlb_remote_flush &&
1344	    !kvm_x86_ops.tlb_remote_flush(kvm))
1345		return 0;
1346	else
1347		return -ENOTSUPP;
1348}
1349
1350void __init kvm_mmu_x86_module_init(void);
1351int kvm_mmu_vendor_module_init(void);
1352void kvm_mmu_vendor_module_exit(void);
1353
1354void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
1355int kvm_mmu_create(struct kvm_vcpu *vcpu);
1356void kvm_mmu_init_vm(struct kvm *kvm);
1357void kvm_mmu_uninit_vm(struct kvm *kvm);
1358void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
1359		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask,
1360		u64 acc_track_mask, u64 me_mask);
1361
1362void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
1363void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
1364				      struct kvm_memory_slot *memslot,
1365				      int start_level);
1366void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
1367				   const struct kvm_memory_slot *memslot);
1368void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
1369				   struct kvm_memory_slot *memslot);
1370void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
1371					struct kvm_memory_slot *memslot);
1372void kvm_mmu_slot_set_dirty(struct kvm *kvm,
1373			    struct kvm_memory_slot *memslot);
1374void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
1375				   struct kvm_memory_slot *slot,
1376				   gfn_t gfn_offset, unsigned long mask);
1377void kvm_mmu_zap_all(struct kvm *kvm);
1378void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
1379unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
1380void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
1381
1382int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
1383bool pdptrs_changed(struct kvm_vcpu *vcpu);
1384
1385int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
1386			  const void *val, int bytes);
1387
1388struct kvm_irq_mask_notifier {
1389	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
1390	int irq;
1391	struct hlist_node link;
1392};
1393
1394void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
1395				    struct kvm_irq_mask_notifier *kimn);
1396void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
1397				      struct kvm_irq_mask_notifier *kimn);
1398void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
1399			     bool mask);
1400
1401extern bool tdp_enabled;
1402
1403u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
1404
1405/* control of guest tsc rate supported? */
1406extern bool kvm_has_tsc_control;
1407/* maximum supported tsc_khz for guests */
1408extern u32  kvm_max_guest_tsc_khz;
1409/* number of bits of the fractional part of the TSC scaling ratio */
1410extern u8   kvm_tsc_scaling_ratio_frac_bits;
1411/* maximum allowed value of TSC scaling ratio */
1412extern u64  kvm_max_tsc_scaling_ratio;
1413/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
1414extern u64  kvm_default_tsc_scaling_ratio;
1415
1416extern u64 kvm_mce_cap_supported;
1417
1418/*
1419 * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing
1420 *			userspace I/O) to indicate that the emulation context
1421 *			should be resued as is, i.e. skip initialization of
1422 *			emulation context, instruction fetch and decode.
1423 *
1424 * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware.
1425 *		      Indicates that only select instructions (tagged with
1426 *		      EmulateOnUD) should be emulated (to minimize the emulator
1427 *		      attack surface).  See also EMULTYPE_TRAP_UD_FORCED.
1428 *
1429 * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to
1430 *		   decode the instruction length.  For use *only* by
1431 *		   kvm_x86_ops.skip_emulated_instruction() implementations.
1432 *
1433 * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to
1434 *			     retry native execution under certain conditions,
1435 *			     Can only be set in conjunction with EMULTYPE_PF.
1436 *
1437 * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was
1438 *			     triggered by KVM's magic "force emulation" prefix,
1439 *			     which is opt in via module param (off by default).
1440 *			     Bypasses EmulateOnUD restriction despite emulating
1441 *			     due to an intercepted #UD (see EMULTYPE_TRAP_UD).
1442 *			     Used to test the full emulator from userspace.
1443 *
1444 * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware
1445 *			backdoor emulation, which is opt in via module param.
1446 *			VMware backoor emulation handles select instructions
1447 *			and reinjects the #GP for all other cases.
1448 *
1449 * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which
1450 *		 case the CR2/GPA value pass on the stack is valid.
1451 */
1452#define EMULTYPE_NO_DECODE	    (1 << 0)
1453#define EMULTYPE_TRAP_UD	    (1 << 1)
1454#define EMULTYPE_SKIP		    (1 << 2)
1455#define EMULTYPE_ALLOW_RETRY_PF	    (1 << 3)
1456#define EMULTYPE_TRAP_UD_FORCED	    (1 << 4)
1457#define EMULTYPE_VMWARE_GP	    (1 << 5)
1458#define EMULTYPE_PF		    (1 << 6)
1459
1460int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
1461int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
1462					void *insn, int insn_len);
1463
1464void kvm_enable_efer_bits(u64);
1465bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
1466int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
1467int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
1468int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
1469int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu);
1470int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu);
1471
1472int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in);
1473int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
1474int kvm_emulate_halt(struct kvm_vcpu *vcpu);
1475int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
1476int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
1477
1478void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
1479int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
1480void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
1481
1482int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
1483		    int reason, bool has_error_code, u32 error_code);
1484
1485int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
1486int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
1487int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
1488int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
1489int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
1490int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
1491unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
1492void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
1493void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
1494int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
1495
1496int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
1497int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
1498
1499unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
1500void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
1501bool kvm_rdpmc(struct kvm_vcpu *vcpu);
1502
1503void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
1504void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
1505void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
1506void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
1507void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
1508void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
1509bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
1510				    struct x86_exception *fault);
1511int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
1512			    gfn_t gfn, void *data, int offset, int len,
1513			    u32 access);
1514bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
1515bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr);
1516
1517static inline int __kvm_irq_line_state(unsigned long *irq_state,
1518				       int irq_source_id, int level)
1519{
1520	/* Logical OR for level trig interrupt */
1521	if (level)
1522		__set_bit(irq_source_id, irq_state);
1523	else
1524		__clear_bit(irq_source_id, irq_state);
1525
1526	return !!(*irq_state);
1527}
1528
1529#define KVM_MMU_ROOT_CURRENT		BIT(0)
1530#define KVM_MMU_ROOT_PREVIOUS(i)	BIT(1+i)
1531#define KVM_MMU_ROOTS_ALL		(~0UL)
1532
1533int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
1534void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
1535
1536void kvm_inject_nmi(struct kvm_vcpu *vcpu);
1537
1538void kvm_update_dr7(struct kvm_vcpu *vcpu);
1539
1540int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
1541int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
1542void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
1543int kvm_mmu_load(struct kvm_vcpu *vcpu);
1544void kvm_mmu_unload(struct kvm_vcpu *vcpu);
1545void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
1546void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
1547			ulong roots_to_free);
1548gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
1549			   struct x86_exception *exception);
1550gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
1551			      struct x86_exception *exception);
1552gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
1553			       struct x86_exception *exception);
1554gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
1555			       struct x86_exception *exception);
1556gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
1557				struct x86_exception *exception);
1558
1559bool kvm_apicv_activated(struct kvm *kvm);
1560void kvm_apicv_init(struct kvm *kvm, bool enable);
1561void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
1562void kvm_request_apicv_update(struct kvm *kvm, bool activate,
1563			      unsigned long bit);
1564
1565int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
1566
1567int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
1568		       void *insn, int insn_len);
1569void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
1570void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
1571			    gva_t gva, hpa_t root_hpa);
1572void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
1573void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
1574		     bool skip_mmu_sync);
1575
1576void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level,
1577		       int tdp_huge_page_level);
1578
1579static inline u16 kvm_read_ldt(void)
1580{
1581	u16 ldt;
1582	asm("sldt %0" : "=g"(ldt));
1583	return ldt;
1584}
1585
1586static inline void kvm_load_ldt(u16 sel)
1587{
1588	asm("lldt %0" : : "rm"(sel));
1589}
1590
1591#ifdef CONFIG_X86_64
1592static inline unsigned long read_msr(unsigned long msr)
1593{
1594	u64 value;
1595
1596	rdmsrl(msr, value);
1597	return value;
1598}
1599#endif
1600
1601static inline u32 get_rdx_init_val(void)
1602{
1603	return 0x600; /* P6 family */
1604}
1605
1606static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
1607{
1608	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
1609}
1610
1611#define TSS_IOPB_BASE_OFFSET 0x66
1612#define TSS_BASE_SIZE 0x68
1613#define TSS_IOPB_SIZE (65536 / 8)
1614#define TSS_REDIRECTION_SIZE (256 / 8)
1615#define RMODE_TSS_SIZE							\
1616	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
1617
1618enum {
1619	TASK_SWITCH_CALL = 0,
1620	TASK_SWITCH_IRET = 1,
1621	TASK_SWITCH_JMP = 2,
1622	TASK_SWITCH_GATE = 3,
1623};
1624
1625#define HF_GIF_MASK		(1 << 0)
1626#define HF_NMI_MASK		(1 << 3)
1627#define HF_IRET_MASK		(1 << 4)
1628#define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
1629#define HF_SMM_MASK		(1 << 6)
1630#define HF_SMM_INSIDE_NMI_MASK	(1 << 7)
1631
1632#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
1633#define KVM_ADDRESS_SPACE_NUM 2
1634
1635#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
1636#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
1637
1638asmlinkage void kvm_spurious_fault(void);
1639
1640/*
1641 * Hardware virtualization extension instructions may fault if a
1642 * reboot turns off virtualization while processes are running.
1643 * Usually after catching the fault we just panic; during reboot
1644 * instead the instruction is ignored.
1645 */
1646#define __kvm_handle_fault_on_reboot(insn)				\
1647	"666: \n\t"							\
1648	insn "\n\t"							\
1649	"jmp	668f \n\t"						\
1650	"667: \n\t"							\
1651	"1: \n\t"							\
1652	".pushsection .discard.instr_begin \n\t"			\
1653	".long 1b - . \n\t"						\
1654	".popsection \n\t"						\
1655	"call	kvm_spurious_fault \n\t"				\
1656	"1: \n\t"							\
1657	".pushsection .discard.instr_end \n\t"				\
1658	".long 1b - . \n\t"						\
1659	".popsection \n\t"						\
1660	"668: \n\t"							\
1661	_ASM_EXTABLE(666b, 667b)
1662
1663#define KVM_ARCH_WANT_MMU_NOTIFIER
1664int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
1665			unsigned flags);
1666int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
1667int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
1668int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
1669int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
1670int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
1671int kvm_cpu_has_extint(struct kvm_vcpu *v);
1672int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
1673int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
1674void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
1675void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
1676
1677int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
1678		    unsigned long ipi_bitmap_high, u32 min,
1679		    unsigned long icr, int op_64_bit);
1680
1681void kvm_define_user_return_msr(unsigned index, u32 msr);
1682int kvm_probe_user_return_msr(u32 msr);
1683int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
1684
1685u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc);
1686u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);
1687
1688unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
1689bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
1690
1691void kvm_make_mclock_inprogress_request(struct kvm *kvm);
1692void kvm_make_scan_ioapic_request(struct kvm *kvm);
1693void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
1694				       unsigned long *vcpu_bitmap);
1695
1696bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
1697				     struct kvm_async_pf *work);
1698void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
1699				 struct kvm_async_pf *work);
1700void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
1701			       struct kvm_async_pf *work);
1702void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
1703bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
1704extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
1705
1706int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
1707int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
1708void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
1709
1710int kvm_is_in_guest(void);
1711
1712int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
1713bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
1714bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
1715
1716bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
1717			     struct kvm_vcpu **dest_vcpu);
1718
1719void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
1720		     struct kvm_lapic_irq *irq);
1721
1722static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
1723{
1724	/* We can only post Fixed and LowPrio IRQs */
1725	return (irq->delivery_mode == APIC_DM_FIXED ||
1726		irq->delivery_mode == APIC_DM_LOWEST);
1727}
1728
1729static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
1730{
1731	if (kvm_x86_ops.vcpu_blocking)
1732		kvm_x86_ops.vcpu_blocking(vcpu);
1733}
1734
1735static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
1736{
1737	if (kvm_x86_ops.vcpu_unblocking)
1738		kvm_x86_ops.vcpu_unblocking(vcpu);
1739}
1740
1741static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
1742
1743static inline int kvm_cpu_get_apicid(int mps_cpu)
1744{
1745#ifdef CONFIG_X86_LOCAL_APIC
1746	return default_cpu_present_to_apicid(mps_cpu);
1747#else
1748	WARN_ON_ONCE(1);
1749	return BAD_APICID;
1750#endif
1751}
1752
1753#define put_smstate(type, buf, offset, val)                      \
1754	*(type *)((buf) + (offset) - 0x7e00) = val
1755
1756#define GET_SMSTATE(type, buf, offset)		\
1757	(*(type *)((buf) + (offset) - 0x7e00))
1758
1759#endif /* _ASM_X86_KVM_HOST_H */
1760